© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98597
    Prev
    Next
    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     now
    -1.42
     zarówno
    -1.03
     to
    -0.98
    ఈ
    -0.98
     inscripción
    -0.97
    ではなく
    -0.96
    stanz
    -0.96
     configureStore
    -0.96
     bukanlah
    -0.95
     خمس
    -0.94
    POSITIVE LOGITS
    дцать
    0.99
     GENT
    0.89
    Known
    0.88
    behind
    0.88
    neath
    0.87
     aastal
    0.85
    為に
    0.85
     kõ
    0.83
    ようですが
    0.82
    Shift
    0.81
    Activations Density 0.001%

    No Known Activations